Endangered Biodiversity

Wildlife Tracking and Modeling of Endangered Animals

Pantanal is a rich ecosystem that houses a big number of wildlife animals, including reptile, amphibian, bird and mammal species. However, with the expansion of agriculture, Pantanal biome needs to conciliate the demand for rural development while conserving biodiversity. Similarly, areas of power plant dams have intentionally flooded big portions of land with the goal to generate more and more power, but affecting the envionroment around. Thus, it is urgent to track and estimate the population to understand the impact of the power industry and of agricultural activities on Pantanal's biodiversity. The aim of this project is to identify automatically the species of endangered animals and help ecologists/biologists to manage the population of animals in wetlands.

Image Acquisition using Thermal and Visual Cameras

Images Captured with Camera Traps

Images from Small Unmanned Aerial Vehicles (UAVs)

Image-based System for Animal Identification

Camera traps are remotely activated devices equipped with a motion sensor that have been widely used by ecologists and biologists. Tipically, they are placed in dense vegetation in order to monitoring wildlife animals. However, it is very complex for researches to set camera traps in wetlands, including power plant dams and in the Pantanal biome. That is because in such areas are concentrated portions of land where small vegetation is mixed with water, therefore, UAVs are suitable tools to capture images and videos of animals. To this end, we can adapt different thermal and visual cameras and create specific flight plans to cover the whole area to be analyzed.

Hydropower Plants

Brazil is a large producer of energy using hydropower plants. Although hydroelectricity has been considered a renewable source of energy, some hydropower plants use dams to store river water in a reservoir. Water is released from the reservoir flows through a turbine, which in turn activates a generator to produce electricity. In Brazil, many dams were built in the boundary of the states of Mato Grosso do Sul and São Paulo. The image shows four dams listed below with their capacity to produce power:

  1. Ilha Solteira (3,444.0 MW)
  2. Três Irmãos (807.5 MW)
  3. Jupiá (1,522.2 MW)
  4. Porto Primavera (1,540.0 MW)

The scope of this project is to monitoring the hydropower plant of Ilha Solteira-SP (Point 1) and Três Lagoas-MS (Point 3). Images will be captured along the reservoir using UAVs, equipped with dual sensor cameras, and convolutional neural networks will be used to identify the animal species and then to estimate its population.

Publications of the Project

Thermal Image Segmentation in Studies of Wildlife Animals

Workshop of Computer Vision, 2015
Mauro Santos et al.

Recognition of Pantanal Animal Species using Convolutional Neural Networks

Workshop of Computer Vision, 2016
Diogo Gonçalves et al.

Recognition of Endangered Pantanal Animal Species using Deep Learning Methods

International Joint Conference on Neural Networks, 2018
Mauro Santos et al.